System

Abstract

An object of a system according to an embodiment is to semi-automate a process of expense settlement and reduce a work load of an employee.SOLUTION: A system includes a reception part, an analysis part, a generation part, and a confirmation part. The registrar uploads the expense receipt or invoice. The analysis unit analyzes the document uploaded by the reception unit and extracts necessary information. The generation unit automatically generates an application form for expense settlement based on the information extracted by the analysis unit. The confirmation unit confirms the application form generated by the generation unit and corrects the application form as necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the expense reimbursement process was often done manually, which placed a heavy workload on employees.

[0005] The system according to the embodiment aims to semi-automate the expense settlement process and reduce the workload of employees. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit uploads expense receipts or invoices. The analysis unit analyzes the documents uploaded by the reception unit and extracts necessary information. The generation unit automatically generates an expense reimbursement application form based on the information extracted by the analysis unit. The confirmation unit checks the application form generated by the generation unit and modifies it as necessary. [Effects of the Invention]

[0007] The system according to the embodiment semi-automates the expense settlement process and can reduce the workload of employees. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) In an embodiment of the present invention, an expense reimbursement system uploads expense receipts and invoices, analyzes them using AI to extract necessary information, and automatically generates and confirms / corrects expense reimbursement application forms. In this system, employees upload expense receipts and invoices to the system, and AI analyzes the uploaded documents and extracts necessary information. For example, it automatically reads information such as the date, amount, and payee. Furthermore, the AI ​​automatically generates expense reimbursement application forms based on the extracted information. The employee then reviews the generated application form and makes any necessary corrections. Finally, the corrected application form is submitted to the system. For example, the expense reimbursement system can also scan paper documents and upload them as PDF files. For example, receipts for travel and accommodation expenses from a business trip can be photographed with a smartphone and uploaded to the system. The expense reimbursement system then analyzes the uploaded documents using AI. The AI ​​uses OCR (optical character recognition) technology to read the contents of the documents and extract necessary information. For example, it can automatically read information such as the receipt date, amount, and payee. This eliminates the need for manual data entry and improves work efficiency. Furthermore, the expense reimbursement system automatically generates expense reimbursement application forms based on the information extracted by AI. For example, the AI ​​automatically enters the expense type and amount based on the information it reads, creating the application form. Employees review the generated application form and make corrections as necessary. For example, if the amount read by the AI ​​is incorrect, employees can manually correct it. Finally, the expense reimbursement system submits the corrected application form to the system. The system manages the submitted application form and automates the approval process. For example, if a supervisor's approval is required, the system automatically notifies the supervisor and requests approval. In this way, expense reimbursement work is semi-automated, reducing the workload on employees. This improves the efficiency of expense reimbursement work and reduces the workload on employees. For example, manual data entry is no longer necessary, reducing work time. Furthermore, automating the application form creation and approval process reduces errors and improves the accuracy of reimbursement work. This allows employees to focus on their core tasks, improving overall work efficiency.This allows the expense reimbursement system to semi-automate expense reimbursement work and reduce the workload of employees. For example, manual data entry is no longer necessary, reducing work time. In addition, automating the application form creation and approval process reduces errors and improves the accuracy of reimbursement work. This allows employees to focus on their core tasks, improving overall work efficiency.

[0029] The expense reimbursement system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit uploads expense receipts or invoices. Expense receipts or invoices include, but are not limited to, paper receipts, electronic receipts, and PDF invoices. The reception unit, for example, digitizes and uploads paper documents using scanning technology. The reception unit can also directly upload documents submitted in digital format. The reception unit can also read printed documents using OCR technology. For example, the reception unit can scan handwritten receipts with a high-resolution scanner and convert them into text information using OCR technology. Digital documents submitted in a specific file format can be directly uploaded. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit uses AI to analyze the documents uploaded by the reception unit and extract necessary information. The analysis is performed using, for example, OCR technology, but is not limited to, the example. For example, the analysis unit may use OCR technology to automatically read information such as the date, amount, and payee of a receipt. The analysis unit may also use AI or perform manual verification. The analysis unit may also use AI to extract and analyze important portions of text. For example, the analysis unit may use OCR technology to automatically read information such as the date, amount, and payee of a receipt. The generation unit may use AI to automatically generate an expense reimbursement application form based on the information extracted by the analysis unit. Automatic generation may be performed, for example, using a template, but is not limited to this example. For example, the generation unit may use AI to automatically input the type and amount of expenses to create an application form. The generation unit may also use AI to perform manual verification. The generation unit may also use AI to extract important portions of text to create an application form. For example, the generation unit may use AI to automatically input the type and amount of expenses to create an application form. The verification unit may verify the application form generated by the generation unit and correct it as necessary. Verification may be performed, for example, manually, but is not limited to this example. For example, the verification department can manually check the generated application form and correct it if necessary, or the verification department can use AI to automatically check it.Furthermore, the verification unit can use AI to extract and verify important parts of the text. For example, the verification unit manually verifies the generated application form and corrects it as necessary. This allows the expense reimbursement system according to the embodiment to semi-automate the expense reimbursement process and reduce the workload of employees. For example, manual data entry is no longer necessary, reducing work time. Furthermore, automating the application form creation and approval process reduces errors and improves the accuracy of the reimbursement process. This allows employees to focus on their core tasks, improving overall work efficiency.

[0030] The expense settlement system includes an OCR unit that reads the contents of documents using OCR technology. The OCR unit reads the contents of documents using OCR technology. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input the contents of documents into AI, which can then read the contents.

[0031] The expense reimbursement system includes an approval unit that automates the approval process for application forms. The approval unit automates the approval process for application forms. Examples of approval processes include, but are not limited to, requiring approval from a supervisor or approval for amounts above a certain amount. For example, if approval from a supervisor is required, the system automatically notifies the supervisor and requests approval. Alternatively, if approval for amounts above a certain amount is required, the system can automatically request approval. Furthermore, the approval unit can also manually check using AI. For example, if approval from a supervisor is required, the system automatically notifies the supervisor and requests approval. This automates the approval process and improves efficiency. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without AI. For example, the approval unit can input the approval process for application forms into AI, which then automates the approval process.

[0032] The expense reimbursement system includes a notification unit that sends a notification to a supervisor. The notification unit sends the notification to the supervisor. Examples of notifications include, but are not limited to, email notifications, in-app notifications, and SMS notifications. For example, the notification unit sends the notification to the supervisor using email notifications. The notification unit can also send the notification to the supervisor using in-app notifications. The notification unit can also send the notification to the supervisor using SMS notifications. For example, the notification unit sends the notification to the supervisor using email notifications. This allows the notification to be sent automatically to the supervisor. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the notification content into AI, which then sends the notification.

[0033] The reception unit can scan paper documents and upload them as PDF files. Scanning can include, but is not limited to, resolution, scanning speed, file format, and the like. For example, the reception unit can scan paper documents and save them as PDF files. The reception unit can also photograph paper documents using a smartphone camera and save them as PDF files. For example, the reception unit can save paper documents scanned by a scanner as PDF files. This allows paper documents to be digitized and uploaded. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input scanned paper documents into AI, which then saves them as PDF files.

[0034] The analysis unit can automatically read at least one of the receipt's date, amount, and payee information. Examples of automatic reading include, but are not limited to, using OCR technology or manual confirmation. The analysis unit can automatically read the receipt's date, amount, and payee information, for example, using OCR technology. The analysis unit can also manually confirm the information. For example, the analysis unit can automatically read the receipt's date, amount, and payee information using OCR technology. This allows the receipt information to be automatically read. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the receipt information into AI, which then reads the information.

[0035] The generation unit can automatically input the type and amount of expenses and create an application form. Examples of expense types include, but are not limited to, transportation expenses, accommodation expenses, and meals. Examples of amounts include, but are not limited to, a maximum amount and a minimum amount. The generation unit can, for example, use AI to automatically input the type and amount of expenses and create an application form. The generation unit can also manually check the type and amount of expenses. For example, the generation unit can use AI to automatically input the type and amount of expenses and create an application form. This allows the type and amount of expenses to be automatically input and an application form to be created. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the type and amount of expenses into AI, which then creates an application form.

[0036] The confirmation unit can check the generated application form and make corrections as necessary. Corrections include, for example, manual corrections and automatic corrections by the system, but are not limited to these examples. For example, the confirmation unit can manually check the generated application form and make corrections as necessary. The confirmation unit can also use AI to automatically make corrections. For example, the confirmation unit can manually check the generated application form and make corrections as necessary. In this way, the generated application form can be checked and corrected. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, or may be performed without using AI. For example, the confirmation unit can input the generated application form into AI, which then makes corrections.

[0037] The reception unit can analyze the user's past upload history and select the optimal upload method. For example, the reception unit can prioritize and suggest upload methods that the user has frequently used in the past (e.g., uploading from a smartphone). The reception unit can also automatically select the optimal method based on the upload methods that the user has used successfully in the past. Furthermore, the reception unit can also suggest the optimal upload method for a specific time period based on the user's past upload history. For example, the reception unit can prioritize and suggest upload methods that the user has frequently used in the past. This makes it possible to select the optimal upload method based on the user's past history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's past upload history into AI, which can select the optimal upload method.

[0038] When uploading documents, the reception unit can filter the documents based on the user's current projects and areas of interest. For example, the reception unit can prioritize uploading only documents related to the user's current projects. The reception unit can also automatically select and upload highly relevant documents based on the user's areas of interest. Furthermore, if the user has expressed interest in a particular project, the reception unit can prioritize uploading documents related to that project. For example, the reception unit can prioritize uploading only documents related to the user's current projects. This allows documents to be filtered based on the user's projects and areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input data on the user's projects and areas of interest into AI, which can then filter the documents.

[0039] When uploading a document, the reception unit can select the optimal upload means depending on the user's input method. For example, if the user uses voice input, the reception unit uploads the document using voice recognition technology. Furthermore, if the user uses text input, the reception unit can also upload the document using text analysis technology. Furthermore, if the user uses image input, the reception unit can also upload the document using image recognition technology. For example, if the user uses voice input, the reception unit uploads the document using voice recognition technology. This makes it possible to select the optimal upload means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's input method into AI, which can then select the optimal upload means.

[0040] When uploading documents, the reception unit can prioritize uploading highly relevant documents by taking into account the user's geographical location information. For example, if the user is on a business trip, the reception unit can prioritize uploading documents related to the business trip destination. Furthermore, if the user is in a specific area, the reception unit can prioritize uploading documents related to that area. Furthermore, if the user is at home, the reception unit can prioritize uploading documents related to the user's home. For example, if the user is on a business trip, the reception unit can prioritize uploading documents related to the business trip destination. This allows highly relevant documents to be prioritized for upload based on the user's geographical location information. Geographical location information is obtained using technologies such as GPS data and IP addresses. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information into AI, which can then prioritize uploading highly relevant documents.

[0041] The reception unit can analyze the user's social media activity when uploading documents and upload related documents. For example, the reception unit can prioritize uploading documents related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and upload related documents. Furthermore, the reception unit can upload related documents based on the activity of the user's friends on social media. For example, the reception unit prioritizes uploading documents related to places where the user has checked in on social media. This allows related documents to be uploaded based on the user's social media activity. Social media activity is analyzed using data such as the content of posts, the number of likes, and the content of comments. Some or all of the above-mentioned processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input data on the user's social media activity into AI, which can then upload related documents.

[0042] The reception unit can customize the upload method by reflecting the user's past feedback when uploading a document. For example, the reception unit can suggest an optimal upload method based on feedback provided by the user in the past. The reception unit can also preferentially select a specific upload method based on the user's past feedback. Furthermore, the reception unit can customize the upload method by reflecting the user's feedback. For example, the reception unit can suggest an optimal upload method based on feedback provided by the user in the past. This allows the upload method to be customized based on the user's past feedback. The feedback is obtained, for example, as data such as user comments and evaluation points. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback into AI, which can then customize the upload method.

[0043] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the document. For example, the analysis unit performs a detailed analysis on documents with high importance. The analysis unit can also perform a simplified analysis on documents with low importance. Furthermore, the analysis unit can automatically adjust the level of detail of the analysis according to the importance. For example, the analysis unit performs a detailed analysis on documents with high importance. This allows the level of detail of the analysis to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document importance data into AI, which can adjust the level of detail of the analysis.

[0044] During analysis, the analysis unit can apply different analysis algorithms depending on the document category. For example, the analysis unit applies a specific analysis algorithm to receipts. The analysis unit can also apply a different analysis algorithm to invoices. Furthermore, the analysis unit can automatically select the optimal analysis algorithm depending on the document category. For example, the analysis unit applies a specific analysis algorithm to receipts. This allows the optimal analysis algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The analysis algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document category data into AI, which then applies the optimal analysis algorithm.

[0045] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can automatically improve the analysis accuracy by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. This allows the analysis accuracy to be improved by referring to the user's past analysis results. Past analysis results are obtained as data such as past analysis data and evaluations of analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into AI, which can improve the analysis accuracy.

[0046] During analysis, the analysis unit can determine the analysis priority based on the submission date of the document. For example, the analysis unit prioritizes analysis of documents submitted earlier. The analysis unit can also postpone documents submitted later. Furthermore, the analysis unit can automatically determine the analysis priority based on the submission date. For example, the analysis unit prioritizes analysis of documents submitted earlier. This allows the analysis priority to be determined based on the submission date of the document. The submission date is obtained based on criteria such as the submission date or the submission deadline. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document submission date data into AI, which then determines the analysis priority.

[0047] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the documents. For example, the analysis unit prioritizes analysis of highly relevant documents. The analysis unit can also postpone analysis of less relevant documents. Furthermore, the analysis unit can automatically adjust the order of analysis based on the relevance of the documents. For example, the analysis unit prioritizes analysis of highly relevant documents. This allows the order of analysis to be adjusted based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document relevance data into AI, which can then adjust the order of analysis.

[0048] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user does not have technical expertise, the analysis unit can automatically adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. This allows the use of technical terms in the analysis to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the analysis.

[0049] The generation unit can adjust the level of detail in the application form based on the importance of the document when generating it. For example, the generation unit generates a detailed application form for a document with high importance. The generation unit can also generate a simplified application form for a document with low importance. Furthermore, the generation unit can automatically adjust the level of detail in the application form according to the importance. For example, the generation unit generates a detailed application form for a document with high importance. This allows the level of detail in the application form to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document importance data into AI, which can then adjust the level of detail in the application form.

[0050] The generation unit can apply different generation algorithms depending on the document category during generation. For example, the generation unit can apply a specific generation algorithm to receipts. The generation unit can also apply a different generation algorithm to invoices. Furthermore, the generation unit can automatically select the optimal generation algorithm depending on the document category. For example, the generation unit applies a specific generation algorithm to receipts. This allows the optimal generation algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The generation algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document category data into AI, which then applies the optimal generation algorithm.

[0051] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit, for example, adjusts the generation algorithm based on the user's past generation results. The generation unit can also learn specific patterns from the user's past generation results and improve the generation accuracy. Furthermore, the generation unit can automatically improve the generation accuracy by referring to the user's past generation results. For example, the generation unit adjusts the generation algorithm based on the user's past generation results. This allows the generation accuracy to be improved by referring to the user's past generation results. Past generation results are obtained, for example, as data such as past generation data and evaluations of the generation results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the user's past generation result data into AI, which can improve the generation accuracy.

[0052] The generation unit can determine the priority of application forms based on the submission dates of the documents at the time of generation. For example, the generation unit preferentially reflects documents submitted earlier in the application form. The generation unit can also postpone documents submitted later. Furthermore, the generation unit can automatically determine the priority of application forms based on the submission dates. For example, the generation unit preferentially reflects documents submitted earlier in the application form. This makes it possible to determine the priority of application forms based on the submission dates of the documents. The submission dates are obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document submission date data into AI, which can then determine the priority of application forms.

[0053] The generation unit can adjust the order of application forms based on the relevance of documents during generation. For example, the generation unit prioritizes reflecting highly relevant documents in the application form. The generation unit can also postpone less relevant documents. Furthermore, the generation unit can automatically adjust the order of application forms based on the relevance of documents. For example, the generation unit prioritizes reflecting highly relevant documents in the application form. This allows the order of application forms to be adjusted based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document relevance data into AI, which can then adjust the order of application forms.

[0054] The generation unit can adjust the use of technical terms in the application form during generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates an application form that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the generation unit can also generate an application form in simple language. Furthermore, the generation unit can automatically adjust the use of technical terms in the application form according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates an application form that uses a lot of technical terms. This allows the use of technical terms in the application form to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's level of expertise data into AI, which then adjusts the use of technical terms in the application form.

[0055] The verification unit can adjust the level of detail of the verification based on the importance of the document during verification. For example, the verification unit performs detailed verification for documents of high importance. The verification unit can also perform simplified verification for documents of low importance. Furthermore, the verification unit can automatically adjust the level of detail of the verification depending on the importance. For example, the verification unit performs detailed verification for documents of high importance. This allows the level of detail of the verification to be adjusted depending on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document importance data into AI, which can adjust the level of detail of the verification.

[0056] The verification unit can apply different verification algorithms depending on the document category during verification. For example, the verification unit can apply a specific verification algorithm to receipts. The verification unit can also apply a different verification algorithm to invoices. Furthermore, the verification unit can automatically select the optimal verification algorithm depending on the document category. For example, the verification unit can apply a specific verification algorithm to receipts. This allows the optimal verification algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The verification algorithm can be realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document category data into AI, which then applies the optimal verification algorithm.

[0057] The verification unit can improve the accuracy of verification by referring to the user's past verification results during verification. The verification unit, for example, adjusts the verification algorithm based on the user's past verification results. The verification unit can also learn specific patterns from the user's past verification results and improve the verification accuracy. Furthermore, the verification unit can automatically improve the verification accuracy by referring to the user's past verification results. For example, the verification unit adjusts the verification algorithm based on the user's past verification results. This allows the verification accuracy to be improved by referring to the user's past verification results. The past verification results are obtained as data such as past verification data and evaluations of the verification results. Some or all of the above-mentioned processing in the verification unit may be performed, for example, using AI, or may be performed without using AI. For example, the verification unit can input the user's past verification result data into AI, which can improve the verification accuracy.

[0058] During confirmation, the confirmation unit can determine the confirmation priority based on the submission date of the document. For example, the confirmation unit prioritizes the confirmation of documents that were submitted earlier. The confirmation unit can also postpone the confirmation of documents that were submitted later. Furthermore, the confirmation unit can automatically determine the confirmation priority based on the submission date. For example, the confirmation unit prioritizes the confirmation of documents that were submitted earlier. This allows the confirmation priority to be determined based on the submission date of the document. The submission date is obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input document submission date data into AI, which can then determine the confirmation priority.

[0059] The verification unit can adjust the order of verification based on the relevance of documents during verification. For example, the verification unit prioritizes verification of highly relevant documents. The verification unit can also postpone verification of less relevant documents. Furthermore, the verification unit can automatically adjust the order of verification based on the relevance of documents. For example, the verification unit prioritizes verification of highly relevant documents. This allows the order of verification to be adjusted based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document relevance data into AI, which can then adjust the order of verification.

[0060] The verification unit can adjust the use of technical terms in the verification depending on the user's level of expertise during verification. For example, if the user has technical expertise, the verification unit can provide a verification method that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the verification unit can also provide a verification method in simple language. Furthermore, the verification unit can automatically adjust the use of technical terms in the verification depending on the user's level of expertise. For example, if the user has technical expertise, the verification unit can provide a verification method that uses a lot of technical terms. This allows the use of technical terms in the verification to be adjusted depending on the user's level of expertise. The level of expertise is evaluated using criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the verification unit can be performed using, for example, AI, or can be performed without AI. For example, the verification unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the verification.

[0061] During OCR, the OCR unit can adjust the level of detail of the reading based on the importance of the document. For example, the OCR unit performs detailed reading for documents of high importance. The OCR unit can also perform simplified reading for documents of low importance. Furthermore, the OCR unit can automatically adjust the level of detail of the reading based on the importance. For example, the OCR unit performs detailed reading for documents of high importance. This allows the level of detail of the reading to be adjusted based on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document importance data into AI, which can then adjust the level of detail of the reading.

[0062] During OCR, the OCR unit can apply different OCR algorithms depending on the document category. For example, the OCR unit applies a specific OCR algorithm to receipts. The OCR unit can also apply a different OCR algorithm to invoices. Furthermore, the OCR unit can automatically select the optimal OCR algorithm depending on the document category. For example, the OCR unit applies a specific OCR algorithm to receipts. This allows the optimal OCR algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The OCR algorithm is realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input document category data into AI, which then applies the optimal OCR algorithm.

[0063] During OCR, the OCR unit can improve reading accuracy by referring to the user's past OCR results. For example, the OCR unit adjusts the OCR algorithm based on the user's past OCR results. The OCR unit can also learn specific patterns from the user's past OCR results to improve reading accuracy. Furthermore, the OCR unit can automatically improve reading accuracy by referring to the user's past OCR results. For example, the OCR unit adjusts the OCR algorithm based on the user's past OCR results. This allows reading accuracy to be improved by referring to the user's past OCR results. Past OCR results are obtained using data such as past OCR data and OCR result evaluations. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input the user's past OCR result data into AI, which can then improve reading accuracy.

[0064] During OCR, the OCR unit can determine the reading priority based on the time of document submission. For example, the OCR unit prioritizes reading documents that were submitted earlier. The OCR unit can also postpone documents that were submitted later. Furthermore, the OCR unit can automatically determine the reading priority based on the submission time. For example, the OCR unit prioritizes reading documents that were submitted earlier. This allows the reading priority to be determined based on the time of document submission. The submission time is obtained based on criteria such as the submission date and submission deadline. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document submission time data into AI, which then determines the reading priority.

[0065] During OCR, the OCR unit can adjust the reading order based on the relevance of the documents. For example, the OCR unit prioritizes reading highly relevant documents. The OCR unit can also postpone documents with low relevance. Furthermore, the OCR unit can automatically adjust the reading order based on the relevance of the documents. For example, the OCR unit prioritizes reading highly relevant documents. This allows the reading order to be adjusted based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document relevance data into AI, which can then adjust the reading order.

[0066] During OCR, the OCR unit can adjust the use of technical terms in the reading depending on the user's level of expertise. For example, if the user has technical expertise, the OCR unit can provide reading results that use a lot of technical terms. Alternatively, if the user does not have technical expertise, the OCR unit can provide reading results in simple language. Furthermore, the OCR unit can automatically adjust the use of technical terms in the reading depending on the user's level of expertise. For example, if the user has technical expertise, the OCR unit can provide reading results that use a lot of technical terms. This allows the use of technical terms in the reading to be adjusted depending on the user's level of expertise. The level of expertise is evaluated based on criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the reading.

[0067] The approval unit can adjust the level of detail of approval based on the importance of the document when approving. For example, the approval unit provides detailed approval for documents of high importance. The approval unit can also provide simplified approval for documents of low importance. Furthermore, the approval unit can automatically adjust the level of detail of approval according to the importance. For example, the approval unit provides detailed approval for documents of high importance. This allows the level of detail of approval to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document importance data into AI, which can adjust the level of detail of approval.

[0068] The approval unit can apply different approval algorithms depending on the document category during approval. For example, the approval unit can apply a specific approval algorithm to receipts. The approval unit can also apply a different approval algorithm to invoices. Furthermore, the approval unit can automatically select the optimal approval algorithm depending on the document category. For example, the approval unit can apply a specific approval algorithm to receipts. This allows the optimal approval algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The approval algorithm can be realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document category data into AI, which then applies the optimal approval algorithm.

[0069] The approval unit can improve the accuracy of approval by referring to the user's past approval results when approving. The approval unit, for example, adjusts the approval algorithm based on the user's past approval results. The approval unit can also learn specific patterns from the user's past approval results and improve the approval accuracy. Furthermore, the approval unit can automatically improve the approval accuracy by referring to the user's past approval results. For example, the approval unit adjusts the approval algorithm based on the user's past approval results. This allows the approval accuracy to be improved by referring to the user's past approval results. The past approval results are obtained as data such as past approval data and evaluations of approval results. Some or all of the above-mentioned processing in the approval unit may be performed, for example, using AI, or may be performed without using AI. For example, the approval unit can input the user's past approval result data into AI, which can improve the approval accuracy.

[0070] The approval department can determine the approval priority based on the time of document submission at the time of approval. For example, the approval department prioritizes approval of documents submitted earlier. The approval department can also postpone documents submitted later. Furthermore, the approval department can automatically determine the approval priority based on the time of submission. For example, the approval department prioritizes approval of documents submitted earlier. This makes it possible to determine the approval priority based on the time of document submission. The submission time is obtained based on criteria such as the submission date and submission deadline. Some or all of the above-mentioned processing in the approval department may be performed using, for example, AI, or may be performed without using AI. For example, the approval department can input document submission time data into AI, which then determines the approval priority.

[0071] The approval department can adjust the approval order based on the relevance of documents during approval. For example, the approval department prioritizes approval of highly relevant documents. The approval department can also postpone approval of less relevant documents. Furthermore, the approval department can automatically adjust the approval order based on the relevance of documents. For example, the approval department prioritizes approval of highly relevant documents. This makes it possible to adjust the approval order based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the approval department may be performed using, for example, AI, or may be performed without using AI. For example, the approval department can input document relevance data into AI, which can then adjust the approval order.

[0072] The approval unit can adjust the use of technical terms in the approval process according to the user's level of expertise. For example, if the user has specialized knowledge, the approval unit can provide an approval method that uses a lot of technical terms. Alternatively, if the user does not have specialized knowledge, the approval unit can provide an approval method in simple language. Furthermore, the approval unit can automatically adjust the use of technical terms in the approval process according to the user's level of expertise. For example, if the user has specialized knowledge, the approval unit can provide an approval method that uses a lot of technical terms. This allows the use of technical terms in the approval process to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the approval unit can be performed using, for example, AI, or can be performed without AI. For example, the approval unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the approval process.

[0073] The notification unit can adjust the level of detail of the notification based on the importance of the document when sending a notification. For example, the notification unit provides detailed notifications for documents with high importance. The notification unit can also provide simplified notifications for documents with low importance. Furthermore, the notification unit can automatically adjust the level of detail of the notification according to the importance. For example, the notification unit provides detailed notifications for documents with high importance. This allows the level of detail of the notification to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document importance data into AI, which can adjust the level of detail of the notification.

[0074] The notification unit can apply different notification algorithms depending on the document category when sending a notification. For example, the notification unit can apply a specific notification algorithm to receipts. The notification unit can also apply a different notification algorithm to invoices. Furthermore, the notification unit can automatically select the optimal notification algorithm depending on the document category. For example, the notification unit can apply a specific notification algorithm to receipts. This allows the optimal notification algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The notification algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document category data into AI, which then applies the optimal notification algorithm.

[0075] The notification unit can improve the accuracy of notifications by referring to the user's past notification results. For example, the notification unit adjusts the notification algorithm based on the user's past notification results. The notification unit can also learn specific patterns from the user's past notification results and improve the accuracy of notifications. Furthermore, the notification unit can automatically improve the accuracy of notifications by referring to the user's past notification results. For example, the notification unit adjusts the notification algorithm based on the user's past notification results. This allows the accuracy of notifications to be improved by referring to the user's past notification results. The past notification results are obtained as data such as past notification data and evaluations of notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's past notification result data into AI, which can improve the accuracy of notifications.

[0076] At the time of notification, the notification unit can determine the priority of notifications based on the submission date of the document. For example, the notification unit prioritizes notifications of documents submitted earlier. The notification unit can also postpone notifications of documents submitted later. Furthermore, the notification unit can automatically determine the priority of notifications based on the submission date. For example, the notification unit prioritizes notifications of documents submitted earlier. This makes it possible to determine the priority of notifications based on the submission date of the document. The submission date is obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document submission date data into AI, which can then determine the priority of notifications.

[0077] The notification unit can adjust the order of notifications based on the relevance of the documents when notifying. For example, the notification unit prioritizes notifications of highly relevant documents. The notification unit can also postpone notifications of less relevant documents. Furthermore, the notification unit can automatically adjust the order of notifications based on the relevance of the documents. For example, the notification unit prioritizes notifications of highly relevant documents. This makes it possible to adjust the order of notifications based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document relevance data into AI, which can then adjust the order of notifications.

[0078] The notification unit can adjust the use of technical terms in the notification depending on the user's level of expertise. For example, if the user has technical expertise, the notification unit can provide a notification method that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the notification unit can automatically adjust the use of technical terms in the notification depending on the user's level of expertise. For example, if the user has technical expertise, the notification unit can provide a notification method that uses a lot of technical terms. This allows the use of technical terms in the notification to be adjusted depending on the user's level of expertise. The level of expertise is evaluated using criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or can be performed without AI. For example, the notification unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the notification.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] The reception unit can analyze the user's past upload history and select the optimal upload method. For example, it can preferentially suggest an upload method that the user has frequently used in the past (e.g., uploading from a smartphone). The reception unit can also automatically select the optimal method based on the upload methods that the user has used successfully in the past. Furthermore, the reception unit can also suggest the optimal upload method for a specific time period based on the user's past upload history. This makes it possible to select the optimal upload method based on the user's past history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past upload history into AI, which can select the optimal upload method.

[0081] The generation unit can adjust the level of detail of the application form based on the importance of the document when generating it. For example, a detailed application form can be generated for a document with high importance. Also, a simplified application form can be generated for a document with low importance. Furthermore, the generation unit can automatically adjust the level of detail of the application form according to the importance. This allows the level of detail of the application form to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document importance data into AI, which can then adjust the level of detail of the application form.

[0082] The approval unit can apply different approval algorithms depending on the document category during approval. For example, a specific approval algorithm can be applied to receipts. A different approval algorithm can also be applied to invoices. Furthermore, the approval unit can automatically select the optimal approval algorithm depending on the document category. This allows the optimal approval algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The approval algorithm is realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document category data into AI, which then applies the optimal approval algorithm.

[0083] During OCR, the OCR unit can adjust the level of detail of the reading based on the importance of the document. For example, detailed reading is performed for documents of high importance. Also, simplified reading can be performed for documents of low importance. Furthermore, the OCR unit can automatically adjust the level of detail of the reading depending on the importance. This allows the level of detail of the reading to be adjusted depending on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document importance data into AI, which can then adjust the level of detail of the reading.

[0084] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. It can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can automatically improve the analysis accuracy by referring to the user's past analysis results. This allows the analysis accuracy to be improved by referring to the user's past analysis results. Past analysis results are obtained, for example, as data such as past analysis data and evaluations of analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis result data into AI, which can then improve the analysis accuracy.

[0085] The approval unit can improve the accuracy of approval by referring to the user's past approval results when approving. For example, the approval algorithm can be adjusted based on the user's past approval results. It can also learn specific patterns from the user's past approval results to improve approval accuracy. Furthermore, the approval unit can automatically improve approval accuracy by referring to the user's past approval results. This allows the accuracy of approval to be improved by referring to the user's past approval results. Past approval results are obtained using data such as past approval data and evaluations of approval results. Some or all of the above-described processing in the approval unit may be performed using, for example, AI, or may be performed without AI. For example, the approval unit can input the user's past approval result data into AI, which can then improve the accuracy of approval.

[0086] The processing flow of the first embodiment will be briefly explained below.

[0087] Step 1: The reception department uploads expense receipts or invoices. Expense receipts or invoices include paper receipts, electronic receipts, and PDF invoices. The reception department digitizes and uploads paper documents using scanning technology. Digitally submitted documents can also be uploaded directly. Printed documents can also be read using OCR technology. For example, a handwritten receipt can be scanned with a high-resolution scanner and converted into text using OCR technology. Digital documents submitted in a specific file format can be uploaded directly. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The analysis unit uses AI to analyze the documents uploaded by the reception unit and extract the necessary information. The analysis is performed using OCR technology. For example, the analysis unit uses OCR technology to automatically read information such as the date, amount, and payee on a receipt. The analysis unit can also use AI to manually check the information. Furthermore, the analysis unit can also use AI to extract and analyze important parts of the text. Step 3: The generation unit uses AI to automatically generate an expense reimbursement application form based on the information extracted by the analysis unit. Automatic generation is performed using a template. For example, the generation unit uses AI to automatically input the type and amount of expenses and create an application form. The generation unit can also use AI to manually check the form. Furthermore, the generation unit can also use AI to extract important parts of the text and create an application form. Step 4: The verification unit checks the application form generated by the generation unit and corrects it if necessary. Verification is performed manually. For example, the verification unit manually checks the generated application form and corrects it if necessary. The verification unit can also use AI to have the system automatically check it. Furthermore, the verification unit can also use AI to extract and check important parts of the text.

[0088] (Example 2) In an embodiment of the present invention, an expense reimbursement system uploads expense receipts and invoices, analyzes them using AI to extract necessary information, and automatically generates and confirms / corrects expense reimbursement application forms. In this system, employees upload expense receipts and invoices to the system, and AI analyzes the uploaded documents and extracts necessary information. For example, it automatically reads information such as the date, amount, and payee. Furthermore, the AI ​​automatically generates expense reimbursement application forms based on the extracted information. The employee then reviews the generated application form and makes any necessary corrections. Finally, the corrected application form is submitted to the system. For example, the expense reimbursement system can also scan paper documents and upload them as PDF files. For example, receipts for travel and accommodation expenses from a business trip can be photographed with a smartphone and uploaded to the system. The expense reimbursement system then analyzes the uploaded documents using AI. The AI ​​uses OCR (optical character recognition) technology to read the contents of the documents and extract necessary information. For example, it can automatically read information such as the receipt date, amount, and payee. This eliminates the need for manual data entry and improves work efficiency. Furthermore, the expense reimbursement system automatically generates expense reimbursement application forms based on the information extracted by AI. For example, the AI ​​automatically enters the expense type and amount based on the information it reads, creating the application form. Employees review the generated application form and make corrections as necessary. For example, if the amount read by the AI ​​is incorrect, employees can manually correct it. Finally, the expense reimbursement system submits the corrected application form to the system. The system manages the submitted application form and automates the approval process. For example, if a supervisor's approval is required, the system automatically notifies the supervisor and requests approval. In this way, expense reimbursement work is semi-automated, reducing the workload on employees. This improves the efficiency of expense reimbursement work and reduces the workload on employees. For example, manual data entry is no longer necessary, reducing work time. Furthermore, automating the application form creation and approval process reduces errors and improves the accuracy of reimbursement work. This allows employees to focus on their core tasks, improving overall work efficiency.This allows the expense reimbursement system to semi-automate expense reimbursement work and reduce the workload of employees. For example, manual data entry is no longer necessary, reducing work time. In addition, automating the application form creation and approval process reduces errors and improves the accuracy of reimbursement work. This allows employees to focus on their core tasks, improving overall work efficiency.

[0089] The expense reimbursement system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit uploads expense receipts or invoices. Expense receipts or invoices include, but are not limited to, paper receipts, electronic receipts, and PDF invoices. The reception unit, for example, digitizes and uploads paper documents using scanning technology. The reception unit can also directly upload documents submitted in digital format. The reception unit can also read printed documents using OCR technology. For example, the reception unit can scan handwritten receipts with a high-resolution scanner and convert them into text information using OCR technology. Digital documents submitted in a specific file format can be directly uploaded. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit uses AI to analyze the documents uploaded by the reception unit and extract necessary information. The analysis is performed using, for example, OCR technology, but is not limited to, the example. For example, the analysis unit may use OCR technology to automatically read information such as the date, amount, and payee of a receipt. The analysis unit may also use AI or perform manual verification. The analysis unit may also use AI to extract and analyze important portions of text. For example, the analysis unit may use OCR technology to automatically read information such as the date, amount, and payee of a receipt. The generation unit may use AI to automatically generate an expense reimbursement application form based on the information extracted by the analysis unit. Automatic generation may be performed, for example, using a template, but is not limited to this example. For example, the generation unit may use AI to automatically input the type and amount of expenses to create an application form. The generation unit may also use AI to perform manual verification. The generation unit may also use AI to extract important portions of text to create an application form. For example, the generation unit may use AI to automatically input the type and amount of expenses to create an application form. The verification unit may verify the application form generated by the generation unit and correct it as necessary. Verification may be performed, for example, manually, but is not limited to this example. For example, the verification department can manually check the generated application form and correct it if necessary, or the verification department can use AI to automatically check it.Furthermore, the verification unit can use AI to extract and verify important parts of the text. For example, the verification unit manually verifies the generated application form and corrects it as necessary. This allows the expense reimbursement system according to the embodiment to semi-automate the expense reimbursement process and reduce the workload of employees. For example, manual data entry is no longer necessary, reducing work time. Furthermore, automating the application form creation and approval process reduces errors and improves the accuracy of the reimbursement process. This allows employees to focus on their core tasks, improving overall work efficiency.

[0090] The expense settlement system includes an OCR unit that reads the contents of documents using OCR technology. The OCR unit reads the contents of documents using OCR technology. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input the contents of documents into AI, which can then read the contents.

[0091] The expense reimbursement system includes an approval unit that automates the approval process for application forms. The approval unit automates the approval process for application forms. Examples of approval processes include, but are not limited to, requiring approval from a supervisor or approval for amounts above a certain amount. For example, if approval from a supervisor is required, the system automatically notifies the supervisor and requests approval. Alternatively, if approval for amounts above a certain amount is required, the system can automatically request approval. Furthermore, the approval unit can also manually check using AI. For example, if approval from a supervisor is required, the system automatically notifies the supervisor and requests approval. This automates the approval process and improves efficiency. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without AI. For example, the approval unit can input the approval process for application forms into AI, which then automates the approval process.

[0092] The expense reimbursement system includes a notification unit that sends a notification to a supervisor. The notification unit sends the notification to the supervisor. Examples of notifications include, but are not limited to, email notifications, in-app notifications, and SMS notifications. For example, the notification unit sends the notification to the supervisor using email notifications. The notification unit can also send the notification to the supervisor using in-app notifications. The notification unit can also send the notification to the supervisor using SMS notifications. For example, the notification unit sends the notification to the supervisor using email notifications. This allows the notification to be sent automatically to the supervisor. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the notification content into AI, which then sends the notification.

[0093] The reception unit can scan paper documents and upload them as PDF files. Scanning can include, but is not limited to, resolution, scanning speed, file format, and the like. For example, the reception unit can scan paper documents and save them as PDF files. The reception unit can also photograph paper documents using a smartphone camera and save them as PDF files. For example, the reception unit can save paper documents scanned by a scanner as PDF files. This allows paper documents to be digitized and uploaded. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input scanned paper documents into AI, which then saves them as PDF files.

[0094] The analysis unit can automatically read at least one of the receipt's date, amount, and payee information. Examples of automatic reading include, but are not limited to, using OCR technology or manual confirmation. The analysis unit can automatically read the receipt's date, amount, and payee information, for example, using OCR technology. The analysis unit can also manually confirm the information. For example, the analysis unit can automatically read the receipt's date, amount, and payee information using OCR technology. This allows the receipt information to be automatically read. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the receipt information into AI, which then reads the information.

[0095] The generation unit can automatically input the type and amount of expenses and create an application form. Examples of expense types include, but are not limited to, transportation expenses, accommodation expenses, and meals. Examples of amounts include, but are not limited to, a maximum amount and a minimum amount. The generation unit can, for example, use AI to automatically input the type and amount of expenses and create an application form. The generation unit can also manually check the type and amount of expenses. For example, the generation unit can use AI to automatically input the type and amount of expenses and create an application form. This allows the type and amount of expenses to be automatically input and an application form to be created. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the type and amount of expenses into AI, which then creates an application form.

[0096] The confirmation unit can check the generated application form and make corrections as necessary. Corrections include, for example, manual corrections and automatic corrections by the system, but are not limited to these examples. For example, the confirmation unit can manually check the generated application form and make corrections as necessary. The confirmation unit can also use AI to automatically make corrections. For example, the confirmation unit can manually check the generated application form and make corrections as necessary. In this way, the generated application form can be checked and corrected. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, or may be performed without using AI. For example, the confirmation unit can input the generated application form into AI, which then makes corrections.

[0097] The reception unit can estimate the user's emotions and adjust the timing of document uploads based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can automatically delay the upload and wait until the user is relaxed. Furthermore, if the user is in a hurry, the reception unit can immediately accelerate the upload and start processing quickly. Furthermore, if the user is relaxed, the reception unit can perform processing at the normal upload timing. For example, if the user is feeling stressed, the reception unit can automatically delay the upload and wait until the user is relaxed. This allows the timing of document uploads to be adjusted according to the user's emotions. Emotion estimation can be achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input the user's emotion data into AI, which can estimate the emotion and adjust the upload timing.

[0098] The reception unit can analyze the user's past upload history and select the optimal upload method. For example, the reception unit can prioritize and suggest upload methods that the user has frequently used in the past (e.g., uploading from a smartphone). The reception unit can also automatically select the optimal method based on the upload methods that the user has used successfully in the past. Furthermore, the reception unit can also suggest the optimal upload method for a specific time period based on the user's past upload history. For example, the reception unit can prioritize and suggest upload methods that the user has frequently used in the past. This makes it possible to select the optimal upload method based on the user's past history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's past upload history into AI, which can select the optimal upload method.

[0099] When uploading documents, the reception unit can filter the documents based on the user's current projects and areas of interest. For example, the reception unit can prioritize uploading only documents related to the user's current projects. The reception unit can also automatically select and upload highly relevant documents based on the user's areas of interest. Furthermore, if the user has expressed interest in a particular project, the reception unit can prioritize uploading documents related to that project. For example, the reception unit can prioritize uploading only documents related to the user's current projects. This allows documents to be filtered based on the user's projects and areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input data on the user's projects and areas of interest into AI, which can then filter the documents.

[0100] When uploading a document, the reception unit can select the optimal upload means depending on the user's input method. For example, if the user uses voice input, the reception unit uploads the document using voice recognition technology. Furthermore, if the user uses text input, the reception unit can also upload the document using text analysis technology. Furthermore, if the user uses image input, the reception unit can also upload the document using image recognition technology. For example, if the user uses voice input, the reception unit uploads the document using voice recognition technology. This makes it possible to select the optimal upload means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's input method into AI, which can then select the optimal upload means.

[0101] The reception unit can estimate the user's emotions and determine the priority of documents to be uploaded based on the estimated user emotions. For example, when the user is feeling stressed, the reception unit postpones uploading less important documents and prioritizes uploading more important documents. The reception unit can also upload documents with normal priority when the user is relaxed. Furthermore, when the user is in a hurry, the reception unit can immediately upload the most important documents. For example, when the user is feeling stressed, the reception unit postpones uploading less important documents and prioritizes uploading more important documents. This allows the priority of documents to be determined according to the user's emotions. Emotion estimation can be achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input the user's emotion data into AI, which can then estimate the emotion and determine the priority of documents.

[0102] When uploading documents, the reception unit can prioritize uploading highly relevant documents by taking into account the user's geographical location information. For example, if the user is on a business trip, the reception unit can prioritize uploading documents related to the business trip destination. Furthermore, if the user is in a specific area, the reception unit can prioritize uploading documents related to that area. Furthermore, if the user is at home, the reception unit can prioritize uploading documents related to the user's home. For example, if the user is on a business trip, the reception unit can prioritize uploading documents related to the business trip destination. This allows highly relevant documents to be prioritized for upload based on the user's geographical location information. Geographical location information is obtained using technologies such as GPS data and IP addresses. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information into AI, which can then prioritize uploading highly relevant documents.

[0103] The reception unit can analyze the user's social media activity when uploading documents and upload related documents. For example, the reception unit can prioritize uploading documents related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and upload related documents. Furthermore, the reception unit can upload related documents based on the activity of the user's friends on social media. For example, the reception unit prioritizes uploading documents related to places where the user has checked in on social media. This allows related documents to be uploaded based on the user's social media activity. Social media activity is analyzed using data such as the content of posts, the number of likes, and the content of comments. Some or all of the above-mentioned processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input data on the user's social media activity into AI, which can then upload related documents.

[0104] The reception unit can customize the upload method by reflecting the user's past feedback when uploading a document. For example, the reception unit can suggest an optimal upload method based on feedback provided by the user in the past. The reception unit can also preferentially select a specific upload method based on the user's past feedback. Furthermore, the reception unit can customize the upload method by reflecting the user's feedback. For example, the reception unit can suggest an optimal upload method based on feedback provided by the user in the past. This allows the upload method to be customized based on the user's past feedback. The feedback is obtained, for example, as data such as user comments and evaluation points. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback into AI, which can then customize the upload method.

[0105] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can provide a simple, highly visible analysis result. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is in a hurry, the analysis unit can provide a more concise analysis result. For example, if the user is feeling stressed, the analysis unit can provide a simple, highly visible analysis result. This allows the way the analysis is presented to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into AI, which can estimate the emotion and adjust the way the analysis is presented.

[0106] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the document. For example, the analysis unit performs a detailed analysis on documents with high importance. The analysis unit can also perform a simplified analysis on documents with low importance. Furthermore, the analysis unit can automatically adjust the level of detail of the analysis according to the importance. For example, the analysis unit performs a detailed analysis on documents with high importance. This allows the level of detail of the analysis to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document importance data into AI, which can adjust the level of detail of the analysis.

[0107] During analysis, the analysis unit can apply different analysis algorithms depending on the document category. For example, the analysis unit applies a specific analysis algorithm to receipts. The analysis unit can also apply a different analysis algorithm to invoices. Furthermore, the analysis unit can automatically select the optimal analysis algorithm depending on the document category. For example, the analysis unit applies a specific analysis algorithm to receipts. This allows the optimal analysis algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The analysis algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document category data into AI, which then applies the optimal analysis algorithm.

[0108] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can automatically improve the analysis accuracy by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. This allows the analysis accuracy to be improved by referring to the user's past analysis results. Past analysis results are obtained as data such as past analysis data and evaluations of analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into AI, which can improve the analysis accuracy.

[0109] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can provide a short and concise analysis result. The analysis unit can also provide a detailed analysis result if the user is relaxed. Furthermore, the analysis unit can provide a quick analysis result if the user is in a hurry. For example, if the user is feeling stressed, the analysis unit can provide a short and concise analysis result. This allows the length of the analysis to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into AI, which then estimates the emotion and adjusts the length of the analysis.

[0110] During analysis, the analysis unit can determine the analysis priority based on the submission date of the document. For example, the analysis unit prioritizes analysis of documents submitted earlier. The analysis unit can also postpone documents submitted later. Furthermore, the analysis unit can automatically determine the analysis priority based on the submission date. For example, the analysis unit prioritizes analysis of documents submitted earlier. This allows the analysis priority to be determined based on the submission date of the document. The submission date is obtained based on criteria such as the submission date or the submission deadline. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document submission date data into AI, which then determines the analysis priority.

[0111] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the documents. For example, the analysis unit prioritizes analysis of highly relevant documents. The analysis unit can also postpone analysis of less relevant documents. Furthermore, the analysis unit can automatically adjust the order of analysis based on the relevance of the documents. For example, the analysis unit prioritizes analysis of highly relevant documents. This allows the order of analysis to be adjusted based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input document relevance data into AI, which can then adjust the order of analysis.

[0112] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user does not have technical expertise, the analysis unit can automatically adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. This allows the use of technical terms in the analysis to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the analysis.

[0113] The generation unit can estimate the user's emotions and adjust the application form generation method based on the estimated user emotions. For example, the generation unit generates a simple application form when the user is stressed. The generation unit can also generate a detailed application form when the user is relaxed. Furthermore, the generation unit can quickly generate an application form when the user is in a hurry. For example, the generation unit generates a simple application form when the user is stressed. This allows the application form generation method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input user emotion data into AI, which then estimates the emotion and adjusts the application form generation method.

[0114] The generation unit can adjust the level of detail in the application form based on the importance of the document when generating it. For example, the generation unit generates a detailed application form for a document with high importance. The generation unit can also generate a simplified application form for a document with low importance. Furthermore, the generation unit can automatically adjust the level of detail in the application form according to the importance. For example, the generation unit generates a detailed application form for a document with high importance. This allows the level of detail in the application form to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document importance data into AI, which can then adjust the level of detail in the application form.

[0115] The generation unit can apply different generation algorithms depending on the document category during generation. For example, the generation unit can apply a specific generation algorithm to receipts. The generation unit can also apply a different generation algorithm to invoices. Furthermore, the generation unit can automatically select the optimal generation algorithm depending on the document category. For example, the generation unit applies a specific generation algorithm to receipts. This allows the optimal generation algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The generation algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document category data into AI, which then applies the optimal generation algorithm.

[0116] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit, for example, adjusts the generation algorithm based on the user's past generation results. The generation unit can also learn specific patterns from the user's past generation results and improve the generation accuracy. Furthermore, the generation unit can automatically improve the generation accuracy by referring to the user's past generation results. For example, the generation unit adjusts the generation algorithm based on the user's past generation results. This allows the generation accuracy to be improved by referring to the user's past generation results. Past generation results are obtained, for example, as data such as past generation data and evaluations of the generation results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the user's past generation result data into AI, which can improve the generation accuracy.

[0117] The generation unit can estimate the user's emotions and adjust the length of the application form based on the estimated user emotions. For example, if the user is feeling stressed, the generation unit can generate a short and to-the-point application form. Furthermore, if the user is relaxed, the generation unit can generate a longer application form with detailed explanations. Furthermore, if the user is in a hurry, the generation unit can quickly generate an application form. For example, if the user is feeling stressed, the generation unit can generate a short and to-the-point application form. This allows the length of the application form to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's emotion data into AI, which can estimate the emotion and adjust the length of the application form.

[0118] The generation unit can determine the priority of application forms based on the submission dates of the documents at the time of generation. For example, the generation unit preferentially reflects documents submitted earlier in the application form. The generation unit can also postpone documents submitted later. Furthermore, the generation unit can automatically determine the priority of application forms based on the submission dates. For example, the generation unit preferentially reflects documents submitted earlier in the application form. This makes it possible to determine the priority of application forms based on the submission dates of the documents. The submission dates are obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document submission date data into AI, which can then determine the priority of application forms.

[0119] The generation unit can adjust the order of application forms based on the relevance of documents during generation. For example, the generation unit prioritizes reflecting highly relevant documents in the application form. The generation unit can also postpone less relevant documents. Furthermore, the generation unit can automatically adjust the order of application forms based on the relevance of documents. For example, the generation unit prioritizes reflecting highly relevant documents in the application form. This allows the order of application forms to be adjusted based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document relevance data into AI, which can then adjust the order of application forms.

[0120] The generation unit can adjust the use of technical terms in the application form during generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates an application form that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the generation unit can also generate an application form in simple language. Furthermore, the generation unit can automatically adjust the use of technical terms in the application form according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates an application form that uses a lot of technical terms. This allows the use of technical terms in the application form to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's level of expertise data into AI, which then adjusts the use of technical terms in the application form.

[0121] The confirmation unit can estimate the user's emotions and adjust the confirmation method based on the estimated user emotions. For example, if the user is feeling stressed, the confirmation unit can provide a simple, highly visible confirmation method. Furthermore, if the user is relaxed, the confirmation unit can also provide a detailed confirmation method. Furthermore, if the user is in a hurry, the confirmation unit can provide a confirmation method that focuses on the main points. For example, if the user is feeling stressed, the confirmation unit can provide a simple, highly visible confirmation method. This allows the confirmation method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's emotion data into AI, which can estimate the emotion and adjust the confirmation method.

[0122] The verification unit can adjust the level of detail of the verification based on the importance of the document during verification. For example, the verification unit performs detailed verification for documents of high importance. The verification unit can also perform simplified verification for documents of low importance. Furthermore, the verification unit can automatically adjust the level of detail of the verification depending on the importance. For example, the verification unit performs detailed verification for documents of high importance. This allows the level of detail of the verification to be adjusted depending on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document importance data into AI, which can adjust the level of detail of the verification.

[0123] The verification unit can apply different verification algorithms depending on the document category during verification. For example, the verification unit can apply a specific verification algorithm to receipts. The verification unit can also apply a different verification algorithm to invoices. Furthermore, the verification unit can automatically select the optimal verification algorithm depending on the document category. For example, the verification unit can apply a specific verification algorithm to receipts. This allows the optimal verification algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The verification algorithm can be realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document category data into AI, which then applies the optimal verification algorithm.

[0124] The verification unit can improve the accuracy of verification by referring to the user's past verification results during verification. The verification unit, for example, adjusts the verification algorithm based on the user's past verification results. The verification unit can also learn specific patterns from the user's past verification results and improve the verification accuracy. Furthermore, the verification unit can automatically improve the verification accuracy by referring to the user's past verification results. For example, the verification unit adjusts the verification algorithm based on the user's past verification results. This allows the verification accuracy to be improved by referring to the user's past verification results. The past verification results are obtained as data such as past verification data and evaluations of the verification results. Some or all of the above-mentioned processing in the verification unit may be performed, for example, using AI, or may be performed without using AI. For example, the verification unit can input the user's past verification result data into AI, which can improve the verification accuracy.

[0125] The confirmation unit can estimate the user's emotions and adjust the length of the confirmation based on the estimated user emotions. For example, if the user is feeling stressed, the confirmation unit can provide a short and to-the-point confirmation method. Furthermore, if the user is relaxed, the confirmation unit can also provide a detailed confirmation method. Furthermore, if the user is in a hurry, the confirmation unit can provide a quick confirmation. For example, if the user is feeling stressed, the confirmation unit can provide a short and to-the-point confirmation method. This allows the length of the confirmation to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without AI. For example, the confirmation unit can input the user's emotion data into AI, which can estimate the emotion and adjust the length of the confirmation.

[0126] During confirmation, the confirmation unit can determine the confirmation priority based on the submission date of the document. For example, the confirmation unit prioritizes the confirmation of documents that were submitted earlier. The confirmation unit can also postpone the confirmation of documents that were submitted later. Furthermore, the confirmation unit can automatically determine the confirmation priority based on the submission date. For example, the confirmation unit prioritizes the confirmation of documents that were submitted earlier. This allows the confirmation priority to be determined based on the submission date of the document. The submission date is obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input document submission date data into AI, which can then determine the confirmation priority.

[0127] The verification unit can adjust the order of verification based on the relevance of documents during verification. For example, the verification unit prioritizes verification of highly relevant documents. The verification unit can also postpone verification of less relevant documents. Furthermore, the verification unit can automatically adjust the order of verification based on the relevance of documents. For example, the verification unit prioritizes verification of highly relevant documents. This allows the order of verification to be adjusted based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input document relevance data into AI, which can then adjust the order of verification.

[0128] The verification unit can adjust the use of technical terms in the verification depending on the user's level of expertise during verification. For example, if the user has technical expertise, the verification unit can provide a verification method that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the verification unit can also provide a verification method in simple language. Furthermore, the verification unit can automatically adjust the use of technical terms in the verification depending on the user's level of expertise. For example, if the user has technical expertise, the verification unit can provide a verification method that uses a lot of technical terms. This allows the use of technical terms in the verification to be adjusted depending on the user's level of expertise. The level of expertise is evaluated using criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the verification unit can be performed using, for example, AI, or can be performed without AI. For example, the verification unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the verification.

[0129] The OCR unit can estimate a user's emotions and adjust the OCR reading accuracy based on the estimated user emotions. For example, if the user is stressed, the OCR unit can increase accuracy and reduce reading errors. The OCR unit can also perform readings with normal accuracy when the user is relaxed. Furthermore, the OCR unit can also perform readings quickly when the user is in a hurry. For example, if the user is stressed, the OCR unit can increase accuracy and reduce reading errors. This allows the OCR reading accuracy to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or without AI. For example, the OCR unit can input user emotion data into AI, which can estimate the emotion and adjust the reading accuracy.

[0130] During OCR, the OCR unit can adjust the level of detail of the reading based on the importance of the document. For example, the OCR unit performs detailed reading for documents of high importance. The OCR unit can also perform simplified reading for documents of low importance. Furthermore, the OCR unit can automatically adjust the level of detail of the reading based on the importance. For example, the OCR unit performs detailed reading for documents of high importance. This allows the level of detail of the reading to be adjusted based on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document importance data into AI, which can then adjust the level of detail of the reading.

[0131] During OCR, the OCR unit can apply different OCR algorithms depending on the document category. For example, the OCR unit applies a specific OCR algorithm to receipts. The OCR unit can also apply a different OCR algorithm to invoices. Furthermore, the OCR unit can automatically select the optimal OCR algorithm depending on the document category. For example, the OCR unit applies a specific OCR algorithm to receipts. This allows the optimal OCR algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The OCR algorithm is realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input document category data into AI, which then applies the optimal OCR algorithm.

[0132] During OCR, the OCR unit can improve reading accuracy by referring to the user's past OCR results. For example, the OCR unit adjusts the OCR algorithm based on the user's past OCR results. The OCR unit can also learn specific patterns from the user's past OCR results to improve reading accuracy. Furthermore, the OCR unit can automatically improve reading accuracy by referring to the user's past OCR results. For example, the OCR unit adjusts the OCR algorithm based on the user's past OCR results. This allows reading accuracy to be improved by referring to the user's past OCR results. Past OCR results are obtained using data such as past OCR data and OCR result evaluations. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input the user's past OCR result data into AI, which can then improve reading accuracy.

[0133] The OCR unit can estimate the user's emotions and adjust the OCR reading speed based on the estimated user emotions. For example, if the user is stressed, the OCR unit can read quickly. Also, if the user is relaxed, the OCR unit can read at a normal speed. Furthermore, if the user is in a hurry, the OCR unit can read at the fastest speed. For example, if the user is stressed, the OCR unit can read quickly. This allows the OCR reading speed to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input the user's emotional data into AI, which can estimate the emotion and adjust the reading speed.

[0134] During OCR, the OCR unit can determine the reading priority based on the time of document submission. For example, the OCR unit prioritizes reading documents that were submitted earlier. The OCR unit can also postpone documents that were submitted later. Furthermore, the OCR unit can automatically determine the reading priority based on the submission time. For example, the OCR unit prioritizes reading documents that were submitted earlier. This allows the reading priority to be determined based on the time of document submission. The submission time is obtained based on criteria such as the submission date and submission deadline. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document submission time data into AI, which then determines the reading priority.

[0135] During OCR, the OCR unit can adjust the reading order based on the relevance of the documents. For example, the OCR unit prioritizes reading highly relevant documents. The OCR unit can also postpone documents with low relevance. Furthermore, the OCR unit can automatically adjust the reading order based on the relevance of the documents. For example, the OCR unit prioritizes reading highly relevant documents. This allows the reading order to be adjusted based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document relevance data into AI, which can then adjust the reading order.

[0136] During OCR, the OCR unit can adjust the use of technical terms in the reading depending on the user's level of expertise. For example, if the user has technical expertise, the OCR unit can provide reading results that use a lot of technical terms. Alternatively, if the user does not have technical expertise, the OCR unit can provide reading results in simple language. Furthermore, the OCR unit can automatically adjust the use of technical terms in the reading depending on the user's level of expertise. For example, if the user has technical expertise, the OCR unit can provide reading results that use a lot of technical terms. This allows the use of technical terms in the reading to be adjusted depending on the user's level of expertise. The level of expertise is evaluated based on criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the OCR unit may be performed using, for example, AI, or may be performed without AI. For example, the OCR unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the reading.

[0137] The approval unit can estimate the user's emotions and adjust the approval method based on the estimated user emotions. For example, if the user is feeling stressed, the approval unit can provide a simple and highly visible approval method. Furthermore, if the user is relaxed, the approval unit can also provide a detailed approval method. Furthermore, if the user is in a hurry, the approval unit can provide a more concise approval method. For example, if the user is feeling stressed, the approval unit can provide a simple and highly visible approval method. This allows the approval method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the approval unit may be performed using, for example, AI, or may be performed without AI. For example, the approval unit can input the user's emotion data into AI, which can estimate the emotion and adjust the approval method.

[0138] The approval unit can adjust the level of detail of approval based on the importance of the document when approving. For example, the approval unit provides detailed approval for documents of high importance. The approval unit can also provide simplified approval for documents of low importance. Furthermore, the approval unit can automatically adjust the level of detail of approval according to the importance. For example, the approval unit provides detailed approval for documents of high importance. This allows the level of detail of approval to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document importance data into AI, which can adjust the level of detail of approval.

[0139] The approval unit can apply different approval algorithms depending on the document category during approval. For example, the approval unit can apply a specific approval algorithm to receipts. The approval unit can also apply a different approval algorithm to invoices. Furthermore, the approval unit can automatically select the optimal approval algorithm depending on the document category. For example, the approval unit can apply a specific approval algorithm to receipts. This allows the optimal approval algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The approval algorithm can be realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document category data into AI, which then applies the optimal approval algorithm.

[0140] The approval unit can improve the accuracy of approval by referring to the user's past approval results when approving. The approval unit, for example, adjusts the approval algorithm based on the user's past approval results. The approval unit can also learn specific patterns from the user's past approval results and improve the approval accuracy. Furthermore, the approval unit can automatically improve the approval accuracy by referring to the user's past approval results. For example, the approval unit adjusts the approval algorithm based on the user's past approval results. This allows the approval accuracy to be improved by referring to the user's past approval results. The past approval results are obtained as data such as past approval data and evaluations of approval results. Some or all of the above-mentioned processing in the approval unit may be performed, for example, using AI, or may be performed without using AI. For example, the approval unit can input the user's past approval result data into AI, which can improve the approval accuracy.

[0141] The approval unit can estimate the user's emotions and adjust the length of the approval based on the estimated user emotions. For example, if the user is feeling stressed, the approval unit can provide a short and concise approval method. Furthermore, if the user is relaxed, the approval unit can also provide a detailed approval method. Furthermore, if the user is in a hurry, the approval unit can provide a quick approval. For example, if the user is feeling stressed, the approval unit can provide a short and concise approval method. This allows the length of the approval to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the approval unit may be performed using, for example, AI, or may be performed without AI. For example, the approval unit can input the user's emotion data into AI, which can estimate the emotion and adjust the length of the approval.

[0142] The approval department can determine the approval priority based on the time of document submission at the time of approval. For example, the approval department prioritizes approval of documents submitted earlier. The approval department can also postpone documents submitted later. Furthermore, the approval department can automatically determine the approval priority based on the time of submission. For example, the approval department prioritizes approval of documents submitted earlier. This makes it possible to determine the approval priority based on the time of document submission. The submission time is obtained based on criteria such as the submission date and submission deadline. Some or all of the above-mentioned processing in the approval department may be performed using, for example, AI, or may be performed without using AI. For example, the approval department can input document submission time data into AI, which then determines the approval priority.

[0143] The approval department can adjust the approval order based on the relevance of documents during approval. For example, the approval department prioritizes approval of highly relevant documents. The approval department can also postpone approval of less relevant documents. Furthermore, the approval department can automatically adjust the approval order based on the relevance of documents. For example, the approval department prioritizes approval of highly relevant documents. This makes it possible to adjust the approval order based on the relevance of documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the approval department may be performed using, for example, AI, or may be performed without using AI. For example, the approval department can input document relevance data into AI, which can then adjust the approval order.

[0144] The approval unit can adjust the use of technical terms in the approval process according to the user's level of expertise. For example, if the user has specialized knowledge, the approval unit can provide an approval method that uses a lot of technical terms. Alternatively, if the user does not have specialized knowledge, the approval unit can provide an approval method in simple language. Furthermore, the approval unit can automatically adjust the use of technical terms in the approval process according to the user's level of expertise. For example, if the user has specialized knowledge, the approval unit can provide an approval method that uses a lot of technical terms. This allows the use of technical terms in the approval process to be adjusted according to the user's level of expertise. The level of expertise is evaluated according to criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the approval unit can be performed using, for example, AI, or can be performed without AI. For example, the approval unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the approval process.

[0145] The notification unit can estimate the user's emotions and adjust the notification method based on the estimated user's emotions. For example, if the user is feeling stressed, the notification unit can provide a simple, highly visible notification method. Furthermore, if the user is relaxed, the notification unit can also provide a detailed notification method. Furthermore, if the user is in a hurry, the notification unit can provide a notification method that focuses on the main points. For example, if the user is feeling stressed, the notification unit can provide a simple, highly visible notification method. This allows the notification method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's emotion data into AI, which can estimate the emotion and adjust the notification method.

[0146] The notification unit can adjust the level of detail of the notification based on the importance of the document when sending a notification. For example, the notification unit provides detailed notifications for documents with high importance. The notification unit can also provide simplified notifications for documents with low importance. Furthermore, the notification unit can automatically adjust the level of detail of the notification according to the importance. For example, the notification unit provides detailed notifications for documents with high importance. This allows the level of detail of the notification to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document importance data into AI, which can adjust the level of detail of the notification.

[0147] The notification unit can apply different notification algorithms depending on the document category when sending a notification. For example, the notification unit can apply a specific notification algorithm to receipts. The notification unit can also apply a different notification algorithm to invoices. Furthermore, the notification unit can automatically select the optimal notification algorithm depending on the document category. For example, the notification unit can apply a specific notification algorithm to receipts. This allows the optimal notification algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The notification algorithm is realized using techniques such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document category data into AI, which then applies the optimal notification algorithm.

[0148] The notification unit can improve the accuracy of notifications by referring to the user's past notification results. For example, the notification unit adjusts the notification algorithm based on the user's past notification results. The notification unit can also learn specific patterns from the user's past notification results and improve the accuracy of notifications. Furthermore, the notification unit can automatically improve the accuracy of notifications by referring to the user's past notification results. For example, the notification unit adjusts the notification algorithm based on the user's past notification results. This allows the accuracy of notifications to be improved by referring to the user's past notification results. The past notification results are obtained as data such as past notification data and evaluations of notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's past notification result data into AI, which can improve the accuracy of notifications.

[0149] The notification unit can estimate the user's emotions and adjust the length of the notification based on the estimated user's emotions. For example, if the user is feeling stressed, the notification unit can provide a short and to-the-point notification. The notification unit can also provide a detailed notification when the user is relaxed. Furthermore, the notification unit can provide a quick notification when the user is in a hurry. For example, if the user is feeling stressed, the notification unit can provide a short and to-the-point notification. This allows the length of the notification to be adjusted according to the user's emotions. The emotion estimation can be achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the user's emotion data into AI, which can estimate the emotion and adjust the length of the notification.

[0150] At the time of notification, the notification unit can determine the priority of notifications based on the submission date of the document. For example, the notification unit prioritizes notifications of documents submitted earlier. The notification unit can also postpone notifications of documents submitted later. Furthermore, the notification unit can automatically determine the priority of notifications based on the submission date. For example, the notification unit prioritizes notifications of documents submitted earlier. This makes it possible to determine the priority of notifications based on the submission date of the document. The submission date is obtained based on criteria such as the submission date and the submission deadline. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document submission date data into AI, which can then determine the priority of notifications.

[0151] The notification unit can adjust the order of notifications based on the relevance of the documents when notifying. For example, the notification unit prioritizes notifications of highly relevant documents. The notification unit can also postpone notifications of less relevant documents. Furthermore, the notification unit can automatically adjust the order of notifications based on the relevance of the documents. For example, the notification unit prioritizes notifications of highly relevant documents. This makes it possible to adjust the order of notifications based on the relevance of the documents. Relevance is evaluated based on criteria such as documents related to the same project or documents in the same category. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input document relevance data into AI, which can then adjust the order of notifications.

[0152] The notification unit can adjust the use of technical terms in the notification depending on the user's level of expertise. For example, if the user has technical expertise, the notification unit can provide a notification method that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the notification unit can automatically adjust the use of technical terms in the notification depending on the user's level of expertise. For example, if the user has technical expertise, the notification unit can provide a notification method that uses a lot of technical terms. This allows the use of technical terms in the notification to be adjusted depending on the user's level of expertise. The level of expertise is evaluated using criteria such as beginner, intermediate, and advanced. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or can be performed without AI. For example, the notification unit can input the user's level of expertise data into AI, which can then adjust the use of technical terms in the notification. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, analysis unit, generation unit, confirmation unit, OCR unit, approval unit, and notification unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, allowing a user to take a photo of a receipt with their smartphone and upload it to the system. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzing the uploaded document using OCR technology and extracting necessary information. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, automatically generating an expense reimbursement application form based on the extracted information. The confirmation unit is implemented, for example, by the control unit 46A of the smart device 14, allowing a user to review the generated application form and revise it as necessary. The OCR unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, reading the contents of the document. The approval unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, automating the application form approval process. The notification unit is realized by, for example, the control unit 46A of the smart device 14, and sends a notification to the superior. === Hard Collateral 1-2 === Each of the above-described elements, including the reception unit, analysis unit, generation unit, confirmation unit, OCR unit, approval unit, and notification unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, allowing a user to take a photo of a receipt with the smart glasses 214 and upload it to the system. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzing the uploaded document using OCR technology and extracting necessary information. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, automatically generating an expense reimbursement application form based on the extracted information. The confirmation unit is implemented, for example, by the control unit 46A of the smart glasses 214, allowing a user to review the generated application form and correct it as necessary. The OCR unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, reading the contents of the document. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automates the approval process of the application. The notification unit is realized, for example, by the control unit 46A of the smart glasses 214, and sends a notification to a superior. === Hard Collateral 1-3 === Each of the above-described elements, including the reception unit, analysis unit, generation unit, confirmation unit, OCR unit, approval unit, and notification unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, allowing a user to take a photo of a receipt using the headset terminal 314 and upload it to the system. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzing the uploaded document using OCR technology and extracting necessary information. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and automatically generating an expense reimbursement application form based on the extracted information. The confirmation unit is implemented, for example, by the control unit 46A of the headset terminal 314, allowing a user to confirm the generated application form and correct it as necessary. The OCR unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and reading the contents of the document. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automates the approval process of the application. The notification unit is realized, for example, by the control unit 46A of the headset type terminal 314, and sends a notification to the superior. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, analysis unit, generation unit, confirmation unit, OCR unit, approval unit, and notification unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, allowing a user to photograph a receipt using the robot 414 and upload it to the system. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzing the uploaded document using OCR technology and extracting necessary information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, automatically generating an expense reimbursement application form based on the extracted information. The confirmation unit is realized, for example, by the control unit 46A of the robot 414, allowing a user to review the generated application form and correct it as necessary. The OCR unit is realized, for example, by the specific processing unit 290 of the data processing device 12, reading the contents of the document. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12, automating the application form approval process. The notification unit is realized by, for example, the control unit 46A of the robot 414, and sends a notification to the superior.

[0153] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0154] The reception unit can analyze the user's past upload history and select the optimal upload method. For example, it can preferentially suggest an upload method that the user has frequently used in the past (e.g., uploading from a smartphone). The reception unit can also automatically select the optimal method based on the upload methods that the user has used successfully in the past. Furthermore, the reception unit can also suggest the optimal upload method for a specific time period based on the user's past upload history. This makes it possible to select the optimal upload method based on the user's past history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past upload history into AI, which can select the optimal upload method.

[0155] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is feeling stressed, a simple, highly visible analysis result can be provided. If the user is relaxed, a detailed analysis result can be provided. Furthermore, if the user is in a hurry, a summary analysis result can be provided. This allows the way the analysis is presented to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's emotion data into AI, which then estimates the emotion and adjusts the way the analysis is presented.

[0156] The generation unit can adjust the level of detail of the application form based on the importance of the document when generating it. For example, a detailed application form can be generated for a document with high importance. Also, a simplified application form can be generated for a document with low importance. Furthermore, the generation unit can automatically adjust the level of detail of the application form according to the importance. This allows the level of detail of the application form to be adjusted according to the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input document importance data into AI, which can then adjust the level of detail of the application form.

[0157] The confirmation unit can estimate the user's emotions and adjust the confirmation method based on the estimated user emotions. For example, if the user is feeling stressed, a simple and highly visible confirmation method can be provided. If the user is relaxed, a detailed confirmation method can be provided. Furthermore, if the user is in a hurry, a confirmation method that focuses on the main points can be provided. This allows the confirmation method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's emotion data into AI, which can estimate the emotion and adjust the confirmation method.

[0158] The approval unit can apply different approval algorithms depending on the document category during approval. For example, a specific approval algorithm can be applied to receipts. A different approval algorithm can also be applied to invoices. Furthermore, the approval unit can automatically select the optimal approval algorithm depending on the document category. This allows the optimal approval algorithm to be applied depending on the document category. Categories are classified based on criteria such as expense type or project type. The approval algorithm is realized using technologies such as machine learning algorithms and rule-based algorithms. Some or all of the above-mentioned processing in the approval unit may be performed using, for example, AI, or may be performed without using AI. For example, the approval unit can input document category data into AI, which then applies the optimal approval algorithm.

[0159] The notification unit can estimate the user's emotions and adjust the notification method based on the estimated user emotions. For example, if the user is feeling stressed, a simple, highly visible notification method can be provided. If the user is relaxed, a detailed notification method can be provided. Furthermore, if the user is in a hurry, a notification method that focuses on the main points can be provided. This allows the notification method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's emotion data into AI, which can estimate the emotion and adjust the notification method.

[0160] During OCR, the OCR unit can adjust the level of detail of the reading based on the importance of the document. For example, detailed reading is performed for documents of high importance. Also, simplified reading can be performed for documents of low importance. Furthermore, the OCR unit can automatically adjust the level of detail of the reading depending on the importance. This allows the level of detail of the reading to be adjusted depending on the importance of the document. The importance is evaluated based on criteria such as the amount of money or the importance of the project. Some or all of the above-mentioned processing in the OCR unit may be performed using, for example, AI, or may be performed without using AI. For example, the OCR unit can input document importance data into AI, which can then adjust the level of detail of the reading.

[0161] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis algorithm can be adjusted based on the user's past analysis results. It can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can automatically improve the analysis accuracy by referring to the user's past analysis results. This allows the analysis accuracy to be improved by referring to the user's past analysis results. Past analysis results are obtained, for example, as data such as past analysis data and evaluations of analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis result data into AI, which can then improve the analysis accuracy.

[0162] The generation unit can estimate the user's emotions and adjust the application form generation method based on the estimated user emotions. For example, if the user is stressed, a simple application form can be generated. On the other hand, if the user is relaxed, a detailed application form can be generated. Furthermore, if the user is in a hurry, a quick application form can be generated. This allows the application form generation method to be adjusted according to the user's emotions. Emotion estimation is achieved using technologies such as facial expression recognition, voice analysis, and text analysis. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user emotion data into AI, which can estimate the emotion and adjust the application form generation method.

[0163] The approval unit can improve the accuracy of approval by referring to the user's past approval results when approving. For example, the approval algorithm can be adjusted based on the user's past approval results. It can also learn specific patterns from the user's past approval results to improve approval accuracy. Furthermore, the approval unit can automatically improve approval accuracy by referring to the user's past approval results. This allows the accuracy of approval to be improved by referring to the user's past approval results. Past approval results are obtained using data such as past approval data and evaluations of approval results. Some or all of the above-described processing in the approval unit may be performed using, for example, AI, or may be performed without AI. For example, the approval unit can input the user's past approval result data into AI, which can then improve the accuracy of approval.

[0164] The processing flow of the second embodiment will be briefly explained below.

[0165] Step 1: The reception department uploads expense receipts or invoices. Expense receipts or invoices include paper receipts, electronic receipts, and PDF invoices. The reception department digitizes and uploads paper documents using scanning technology. Digitally submitted documents can also be uploaded directly. Printed documents can also be read using OCR technology. For example, a handwritten receipt can be scanned with a high-resolution scanner and converted into text using OCR technology. Digital documents submitted in a specific file format can be uploaded directly. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The analysis unit uses AI to analyze the documents uploaded by the reception unit and extract the necessary information. The analysis is performed using OCR technology. For example, the analysis unit uses OCR technology to automatically read information such as the date, amount, and payee on a receipt. The analysis unit can also use AI to manually check the information. Furthermore, the analysis unit can also use AI to extract and analyze important parts of the text. Step 3: The generation unit uses AI to automatically generate an expense reimbursement application form based on the information extracted by the analysis unit. Automatic generation is performed using a template. For example, the generation unit uses AI to automatically input the type and amount of expenses and create an application form. The generation unit can also use AI to manually check the form. Furthermore, the generation unit can also use AI to extract important parts of the text and create an application form. Step 4: The verification unit checks the application form generated by the generation unit and corrects it if necessary. Verification is performed manually. For example, the verification unit manually checks the generated application form and corrects it if necessary. The verification unit can also use AI to have the system automatically check it. Furthermore, the verification unit can also use AI to extract and check important parts of the text.

[0166] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0171] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0172] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0173] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0177] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0187] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0188] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0189] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0190] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0191] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0192] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0193] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0194] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0196] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0198] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0199] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0200] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0201] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0202] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0203] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0204] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0205] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0206] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0208] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0209] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0210] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0211] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0212] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0213] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0214] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0215] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0216] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0217] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0218] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0219] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0220] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0221] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0222] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0223] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0224] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0225] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0226] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0227] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0228] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0229] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0230] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0231] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0232] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0233] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0234] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0235] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0236] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0237] [Explanation of symbols]

[0238] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where expense receipts or invoices are uploaded; an analysis unit that analyzes the document uploaded by the reception unit and extracts necessary information; a generation unit that automatically generates an expense reimbursement application form based on the information extracted by the analysis unit; a confirmation unit that confirms the application form generated by the generation unit and corrects it as necessary. A system characterized by:

2. Equipped with an OCR unit that reads the contents of documents using OCR technology 2. The system of claim 1.

3. Equipped with an approval department that automates the application approval process 2. The system of claim 1.

4. Equipped with a notification section that sends notifications to superiors 2. The system of claim 1.

5. The reception unit Scan your paper documents and upload them as PDF files 2. The system of claim 1.

6. The analysis unit Automatically read at least one of the following information from the receipt: date, amount, and payee 2. The system of claim 1.

7. The generation unit Automatically enter expense types and amounts and create application forms 2. The system of claim 1.

8. The confirmation unit Check the generated application form and make any necessary corrections.

2. The system of claim 1.

9. The reception unit Inferring user emotions and adjusting the timing of document uploads based on the estimated user emotions 2. The system of claim 1.

Images